© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9575
    Prev
    Next
    INDEX
    Explanations

    pokemon names, programming.pokemon names, programming, scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıĻ
    -0.10
    ä¸ĸ家
    -0.10
    æ¤Ĵ
    -0.09
    åıĻè¿°
    -0.09
    天çĦ¶
    -0.09
    æ·¬
    -0.09
    éķ¿èĢģ
    -0.09
     clam
    -0.09
    æľīæĿĥ
    -0.09
    大å®ĹåķĨåĵģ
    -0.09
    POSITIVE LOGITS
    æĿ¯
    0.10
    LAB
    0.09
    顶
    0.08
    ysize
    0.08
    _ib
    0.08
    olk
    0.08
    ä¸ĢæĿ¯
    0.08
    สาร
    0.08
    åħį
    0.08
     Cup
    0.08
    Activations Density 0.038%

    No Known Activations